A robust CRNN-based OCR model for license plate recognition (Persian only). This model is a finetuned version of crnn-base-fa-64x256 on the Persian license plate dataset (v1).

Note that this model only works on a cropped image of a plate, so you have to run an object(license plate) detection model and pass its output to this model to work.

Usage

pip install hezar
from hezar import Model

model = Model.load("hezarai/crnn-fa-64x256-license-plate-recognition")
plate_text = model.predict("assets/license_plate_ocr_example.jpg")
print(plate_text)  # Persian text of mixed numbers and characters might not show correctly in the console
['۵۷س۷۷۹۷۷']